Li et al. (2023) used the Othello board game as a test case for the ability of GPT-2 to induce world models, and were followed up by Nanda et al. (2023b). We briefly discuss the original experiments, expanding them to include more language models with more comprehensive probing. Specifically, we analyze sequences of Othello board states and train the model to predict the next move based on previous moves. We evaluate seven language models (GPT-2, T5, Bart, Flan-T5, Mistral, LLaMA-2, and Qwen2.5) on the Othello task and conclude that these models not only learn to play Othello, but also induce the Othello board layout. We find that all models achieve up to 99% accuracy in unsupervised grounding and exhibit high similarity in the board features they learned. This provides considerably stronger evidence for the Othello World Model Hypothesis than previous works. Li et al. (2023) used the Othello board game to probe the ability of LLMs to induce world models. Their network had a 60-word input vocabulary, corresponding to the 64 tiles of an Othello board, except for the four that are already filled at the start. They trained the network on two datasets: one on about 140,000 real Othello games and another on millions of synthetic games. They then trained 64 independent non-linear probes (two-layer MLP classifiers) to classify each of the 64 tiles into three states: black, blank, and white, using internal representations from Othello-GPT as input.

The game of Othello is one of the world's most complex and popular games that has yet to be computationally solved. Othello has roughly ten octodecillion (10 to the 58th power) possible game records and ten octillion (10 to the 28th power) possible game positions. The challenge of solving Othello, determining the outcome of a game with no mistake made by either player, has long been a grand challenge in computer science. This paper announces a significant milestone: Othello is now solved. It is computationally proved that perfect play by both players lead to a draw. Strong Othello software has long been built using heuristically designed search techniques. Solving a game provides a solution that enables the software to play the game perfectly.

Language models like OpenAI's Generative Pre-Trained Transformers (GPT-2/3) capture the long-term correlations needed to generate text in a variety of domains (such as language translators) and recently in gameplay (chess, Go, and checkers). The present research applies both the larger (GPT-3) and smaller (GPT-2) language models to explore the complex strategies for the game of Othello (or Reverses). Given the game rules for rapid reversals of fortune, the language model not only represents a candidate predictor of the next move based on previous game moves but also avoids sparse rewards in gameplay. The language model automatically captures or emulates championship-level strategies. The fine-tuned GPT-2 model generates Othello games ranging from 13-71% completion, while the larger GPT-3 model reaches 41% of a complete game. Like previous work with chess and Go, these language models offer a novel way to generate plausible game archives, particularly for comparing opening moves across a larger sample than humanly possible to explore. A primary contribution of these models magnifies (by two-fold) the previous record for player archives (120,000 human games over 45 years from 1977-2022), thus supplying the research community with more diverse and original strategies for sampling with other reinforcement learning techniques.

We introduce OLIVAW, an AI Othello player adopting the design principles of the famous AlphaGo series. The main motivation behind OLIVAW was to attain exceptional competence in a non-trivial board game, but at a tiny fraction of the cost of its illustrious predecessors. In this paper we show how OLIVAW successfully met this challenge.

Decision-theoretic control of search has previously used as its basic unit. of computation the generation and evaluation of a complete set of successors. Although this simplifies analysis, it results in some lost opportunities for pruning and satisficing. This paper therefore extends the analysis of the value of computation to cover individual successor evaluations. The analytic techniques used may prove useful for control of reasoning in more general settings. A formula is developed for the expected value of a node, k of whose n successors have been evaluated. This formula is used to estimate the value of expanding further successors, using a general formula for the value of a computation in game-playing developed in earlier work. We exhibit an improved version of the MGSS* algorithm, giving empirical results for the game of Othello.

Othello is a recent addition to the collection of games that have been examined within artificial intelligence. Advances have been rapid, yielding programs that have reached the level of world-championship play. This article describes the current champion Othello program, iago. The work described here includes: (1) a task analysis of Othello; (2) the implementation of a program based on this analysis and state-of-the-art AI game-playing techniques; and (3) an evaluation of the program's performance through games played against other programs and comparisons with expert human play.